© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69343
    Prev
    Next
    INDEX
    Explanations

    book

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lutter
    -0.09
     worldwide
    -0.08
    awner
    -0.08
    ennan
    -0.08
    人才
    -0.08
     Nan
    -0.08
     nous
    -0.08
     Titanic
    -0.08
     Jackson
    -0.08
    Titan
    -0.07
    POSITIVE LOGITS
     notation
    0.08
    kið
    0.08
    .pre
    0.08
    ijkt
    0.08
    .Allow
    0.07
    .Load
    0.07
    ครับ
    0.07
     bmp
    0.07
    .Cal
    0.07
     amo
    0.07
    Activations Density 0.001%

    No Known Activations